Searcharxiv⌕ Search

arXiv subjects

Peter Davies

Publications and source records attributed to Peter Davies.

At least 19 recordsLinked to original sources
arXiv2024

Parallel Derandomization for Coloring

Graph coloring problems are among the most fundamental problems in parallel and distributed computing, and have been studied extensively in both settings. In this context, designing efficient deterministic algorithms for these problems has been found particularly challenging. In this work we consider this challenge, and design a novel framework for derandomizing algorithms for coloring-type problems in the Massively Parallel Computation (MPC) model with sublinear space. We give an application of this framework by showing that a recent $(degree+1)$-list coloring algorithm by Halldorsson et al. (STOC'22) in the LOCAL model of distributed computation can be translated to the MPC model and efficiently derandomized. Our algorithm runs in $O(\log \log \log n)$ rounds, which matches the complexity of the state of the art algorithm for the $(Δ+ 1)$-coloring problem.

cs.DS↗
arXiv2023

Optimal (degree+1)-Coloring in Congested Clique

We consider the distributed complexity of the (degree+1)-list coloring problem, in which each node $u$ of degree $d(u)$ is assigned a palette of $d(u)+1$ colors, and the goal is to find a proper coloring using these color palettes. The (degree+1)-list coloring problem is a natural generalization of the classical $(\Delta+1)$-coloring and $(\Delta+1)$-list coloring problems, both being benchmark problems extensively studied in distributed and parallel computing. In this paper we settle the complexity of the (degree+1)-list coloring problem in the Congested Clique model by showing that it can be solved deterministically in a constant number of rounds.

cs.DS↗
arXiv2023

Uniting General-Graph and Geometric-Based Radio Networks via Independence Number Parametrization

In the study of radio networks, the tasks of broadcasting (propagating a message throughout the network) and leader election (having the network agree on a node to designate `leader') are two of the most fundamental global problems, and have a long history of work devoted to them. This work has two divergent strands: some works focus on exploiting the geometric properties of wireless networks based in physical space, while others consider general graphs. Algorithmic results in each of these avenues have often used quite different techniques, and produced bounds using incomparable parametrizations. In this work, we unite the study of general-graph and geometric-based radio networks, by adapting the broadcast and leader election algorithm of Czumaj and Davies (JACM '21) to achieve a running-time parametrized by the independence number of the network (i.e., the size of the maximum independent set). This parametrization preserves the running time on general graphs, matching the best known, but also improves running times to near-optimality across a wide range of geometric-based graph classes. As part of this algorithm, we also provide the first algorithm for computing a maximal independent set in general-graph radio networks. This algorithm runs in $O(\log^3 n)$ time-steps, only a $\log n$ factor away from the $Ω(\log^2 n)$ lower bound.

cs.DC↗
arXiv2023

Optimal Message-Passing with Noisy Beeps

Beeping models are models for networks of weak devices, such as sensor networks or biological networks. In these networks, nodes are allowed to communicate only via emitting beeps: unary pulses of energy. Listening nodes only the capability of {\it carrier sensing}: they can only distinguish between the presence or absence of a beep, but receive no other information. The noisy beeping model further assumes listening nodes may be disrupted by random noise. Despite this extremely restrictive communication model, it transpires that complex distributed tasks can still be performed by such networks. In this paper we provide an optimal procedure for simulating general message passing in the beeping and noisy beeping models. We show that a round of \textsf{Broadcast CONGEST} can be simulated in $O(Δ\log n)$ round of the noisy (or noiseless) beeping model, and a round of \textsf{CONGEST} can be simulated in $O(Δ^2\log n)$ rounds (where $Δ$ is the maximum degree of the network). We also prove lower bounds demonstrating that no simulation can use asymptotically fewer rounds. This allows a host of graph algorithms to be efficiently implemented in beeping models. As an example, we present an $O(\log n)$-round \textsf{Broadcast CONGEST} algorithm for maximal matching, which, when simulated using our method, immediately implies a near-optimal $O(Δ\log^2 n)$-round maximal matching algorithm in the noisy beeping model.

cs.DC↗
arXiv2022

Improved Distributed Algorithms for the Lovász Local Lemma and Edge Coloring

The Lovász Local Lemma is a classic result in probability theory that is often used to prove the existence of combinatorial objects via the probabilistic method. In its simplest form, it states that if we have $n$ `bad events', each of which occurs with probability at most $p$ and is independent of all but $d$ other events, then under certain criteria on $p$ and $d$, all of the bad events can be avoided with positive probability. While the original proof was existential, there has been much study on the algorithmic Lovász Local Lemma: that is, designing an algorithm which finds an assignment of the underlying random variables such that all the bad events are indeed avoided. Notably, the celebrated result of Moser and Tardos [JACM '10] also implied an efficient distributed algorithm for the problem, running in $O(\log^2 n)$ rounds. For instances with low $d$, this was improved to $O(d^2+\log^{O(1)}\log n)$ by Fischer and Ghaffari [DISC '17], a result that has proven highly important in distributed complexity theory (Chang and Pettie [SICOMP '19]). We give an improved algorithm for the Lovász Local Lemma, providing a trade-off between the strength of the criterion relating $p$ and $d$, and the distributed round complexity. In particular, in the same regime as Fischer and Ghaffari's algorithm, we improve the round complexity to $O(\frac{d}{\log d}+\log^{O(1)}\log n)$. At the other end of the trade-off, we obtain a $\log^{O(1)}\log n$ round complexity for a substantially wider regime than previously known. As our main application, we also give the first $\log^{O(1)}\log n$-round distributed algorithm for the problem of $Δ+o(Δ)$-edge coloring a graph of maximum degree $Δ$. This is an almost exponential improvement over previous results: no prior $\log^{o(1)} n$-round algorithm was known even for $2Δ-2$-edge coloring.

cs.DC↗
arXiv2022

Asynchronous Decentralized SGD with Quantized and Local Updates

Decentralized optimization is emerging as a viable alternative for scalable distributed machine learning, but also introduces new challenges in terms of synchronization costs. To this end, several communication-reduction techniques, such as non-blocking communication, quantization, and local steps, have been explored in the decentralized setting. Due to the complexity of analyzing optimization in such a relaxed setting, this line of work often assumes \emph{global} communication rounds, which require additional synchronization. In this paper, we consider decentralized optimization in the simpler, but harder to analyze, \emph{asynchronous gossip} model, in which communication occurs in discrete, randomly chosen pairings among nodes. Perhaps surprisingly, we show that a variant of SGD called \emph{SwarmSGD} still converges in this setting, even if \emph{non-blocking communication}, \emph{quantization}, and \emph{local steps} are all applied \emph{in conjunction}, and even if the node data distributions and underlying graph topology are both \emph{heterogenous}. Our analysis is based on a new connection with multi-dimensional load-balancing processes. We implement this algorithm and deploy it in a super-computing environment, showing that it can outperform previous decentralized methods in terms of end-to-end training time, and that it can even rival carefully-tuned large-batch SGD for certain tasks.

cs.LG↗
arXiv2021

Collecting Coupons is Faster with Friends

In this note, we introduce a distributed twist on the classic coupon collector problem: a set of $m$ collectors wish to each obtain a set of $n$ coupons; for this, they can each sample coupons uniformly at random, but can also meet in pairwise interactions, during which they can exchange coupons. By doing so, they hope to reduce the number of coupons that must be sampled by each collector in order to obtain a full set. This extension is natural when considering real-world manifestations of the coupon collector phenomenon, and has been remarked upon and studied empirically [Hayes and Hannigan 2006, Ahmad et al. 2014, Delmarcelle 2019]. We provide the first theoretical analysis for such a scenario. We find that "coupon collecting with friends" can indeed significantly reduce the number of coupons each collector must sample, and raises interesting connections to the more traditional variants of the problem. While our analysis is in most cases asymptotically tight, there are several open questions raised, regarding finer-grained analysis of both "coupon collecting with friends", and of a long-studied variant of the original problem in which a collector requires multiple full sets of coupons.

cs.DC↗
arXiv2021

Improved Deterministic $(Δ+1)$-Coloring in Low-Space MPC

We present a deterministic $O(\log \log \log n)$-round low-space Massively Parallel Computation (MPC) algorithm for the classical problem of $(Δ+1)$-coloring on $n$-vertex graphs. In this model, every machine has a sublinear local memory of size $n^ϕ$ for any arbitrary constant $ϕ\in (0,1)$. Our algorithm works under the relaxed setting where each machine is allowed to perform exponential (in $n^ϕ$) local computation, while respecting the $n^ϕ$ space and bandwidth limitations. Our key technical contribution is a novel derandomization of the ingenious $(Δ+1)$-coloring LOCAL algorithm by Chang-Li-Pettie (STOC 2018, SIAM J. Comput. 2020). The Chang-Li-Pettie algorithm runs in $T_{local}=poly(\log\log n)$ rounds, which sets the state-of-the-art randomized round complexity for the problem in the local model. Our derandomization employs a combination of tools, most notably pseudorandom generators (PRG) and bounded-independence hash functions. The achieved round complexity of $O(\log\log\log n)$ rounds matches the bound of $\log(T_{local})$, which currently serves an upper bound barrier for all known randomized algorithms for locally-checkable problems in this model. Furthermore, no deterministic sublogarithmic low-space MPC algorithms for the $(Δ+1)$-coloring problem were previously known.

cs.DS↗
arXiv2021

Distributed Principal Component Analysis with Limited Communication

We study efficient distributed algorithms for the fundamental problem of principal component analysis and leading eigenvector computation on the sphere, when the data are randomly distributed among a set of computational nodes. We propose a new quantized variant of Riemannian gradient descent to solve this problem, and prove that the algorithm converges with high probability under a set of necessary spherical-convexity properties. We give bounds on the number of bits transmitted by the algorithm under common initialization schemes, and investigate the dependency on the problem dimension in each case.

math.OC↗
arXiv2021

Communication-Efficient Distributed Optimization with Quantized Preconditioners

We investigate fast and communication-efficient algorithms for the classic problem of minimizing a sum of strongly convex and smooth functions that are distributed among $n$ different nodes, which can communicate using a limited number of bits. Most previous communication-efficient approaches for this problem are limited to first-order optimization, and therefore have \emph{linear} dependence on the condition number in their communication complexity. We show that this dependence is not inherent: communication-efficient methods can in fact have sublinear dependence on the condition number. For this, we design and analyze the first communication-efficient distributed variants of preconditioned gradient descent for Generalized Linear Models, and for Newton's method. Our results rely on a new technique for quantizing both the preconditioner and the descent direction at each step of the algorithms, while controlling their convergence rate. We also validate our findings experimentally, showing fast convergence and reduced communication.

math.OC↗
arXiv2021

Component Stability in Low-Space Massively Parallel Computation

We study the power and limitations of component-stable algorithms in the low-space model of Massively Parallel Computation (MPC). Recently Ghaffari, Kuhn and Uitto (FOCS 2019) introduced the class of component-stable low-space MPC algorithms, which are, informally, defined as algorithms for which the outputs reported by the nodes in different connected components are required to be independent. This very natural notion was introduced to capture most (if not all) of the known efficient MPC algorithms to date, and it was the first general class of MPC algorithms for which one can show non-trivial conditional lower bounds. In this paper we enhance the framework of component-stable algorithms and investigate its effect on the complexity of randomized and deterministic low-space MPC. Our key contributions include: 1) We revise and formalize the lifting approach of Ghaffari, Kuhn and Uitto. This requires a very delicate amendment of the notion of component stability, which allows us to fill in gaps in the earlier arguments. 2) We also extend the framework to obtain conditional lower bounds for deterministic algorithms and fine-grained lower bounds that depend on the maximum degree $Δ$. 3) We demonstrate a collection of natural graph problems for which non-component-stable algorithms break the conditional lower bound obtained for component-stable algorithms. This implies that, for both deterministic and randomized algorithms, component-stable algorithms are conditionally weaker than the non-component-stable ones. Altogether our results imply that component-stability might limit the computational power of the low-space MPC model, at least in certain contexts, paving the way for improved upper bounds that escape the conditional lower bound setting of Ghaffari, Kuhn, and Uitto.

cs.DS↗
arXiv2021

New Bounds For Distributed Mean Estimation and Variance Reduction

We consider the problem of distributed mean estimation (DME), in which $n$ machines are each given a local $d$-dimensional vector $x_v \in \mathbb{R}^d$, and must cooperate to estimate the mean of their inputs $μ= \frac 1n\sum_{v = 1}^n x_v$, while minimizing total communication cost. DME is a fundamental construct in distributed machine learning, and there has been considerable work on variants of this problem, especially in the context of distributed variance reduction for stochastic gradients in parallel SGD. Previous work typically assumes an upper bound on the norm of the input vectors, and achieves an error bound in terms of this norm. However, in many real applications, the input vectors are concentrated around the correct output $μ$, but $μ$ itself has large norm. In such cases, previous output error bounds perform poorly. In this paper, we show that output error bounds need not depend on input norm. We provide a method of quantization which allows distributed mean estimation to be performed with solution quality dependent only on the distance between inputs, not on input norm, and show an analogous result for distributed variance reduction. The technique is based on a new connection with lattice theory. We also provide lower bounds showing that the communication to error trade-off of our algorithms is asymptotically optimal. As the lattices achieving optimal bounds under $\ell_2$-norm can be computationally impractical, we also present an extension which leverages easy-to-use cubic lattices, and is loose only up to a logarithmic factor in $d$. We show experimentally that our method yields practical improvements for common applications, relative to prior approaches.

cs.LG↗
arXiv2020

Simple, Deterministic, Constant-Round Coloring in the Congested Clique

We settle the complexity of the $(Δ+1)$-coloring and $(Δ+1)$-list coloring problems in the CONGESTED CLIQUE model by presenting a simple deterministic algorithm for both problems running in a constant number of rounds. This matches the complexity of the recent breakthrough randomized constant-round $(Δ+1)$-list coloring algorithm due to Chang et al. (PODC'19), and significantly improves upon the state-of-the-art $O(\log Δ)$-round deterministic $(Δ+1)$-coloring bound of Parter (ICALP'18). A remarkable property of our algorithm is its simplicity. Whereas the state-of-the-art randomized algorithms for this problem are based on the quite involved local coloring algorithm of Chang et al. (STOC'18), our algorithm can be described in just a few lines. At a high level, it applies a careful derandomization of a recursive procedure which partitions the nodes and their respective palettes into separate bins. We show that after $O(1)$ recursion steps, the remaining uncolored subgraph within each bin has linear size, and thus can be solved locally by collecting it to a single node. This algorithm can also be implemented in the Massively Parallel Computation (MPC) model provided that each machine has linear (in $n$, the number of nodes in the input graph) space. We also show an extension of our algorithm to the MPC regime in which machines have sublinear space: we present the first deterministic $(Δ+1)$-list coloring algorithm designed for sublinear-space MPC, which runs in $O(\log Δ+ \log\log n)$ rounds.

cs.DS↗
arXiv2020

CyRes -- Avoiding Catastrophic Failure in Connected and Autonomous Vehicles (Extended Abstract)

Existing approaches to cyber security and regulation in the automotive sector cannot achieve the quality of outcome necessary to ensure the safe mass deployment of advanced vehicle technologies and smart mobility systems. Without sustainable resilience hard-fought public trust will evaporate, derailing emerging global initiatives to improve the efficiency, safety and environmental impact of future transport. This paper introduces an operational cyber resilience methodology, CyRes, that is suitable for standardisation. The CyRes methodology itself is capable of being tested in court or by publicly appointed regulators. It is designed so that operators understand what evidence should be produced by it and are able to measure the quality of that evidence. The evidence produced is capable of being tested in court or by publicly appointed regulators. Thus, the real-world system to which the CyRes methodology has been applied is capable of operating at all times and in all places with a legally and socially acceptable value of negative consequence.

cs.CR↗
arXiv2020

Graph Sparsification for Derandomizing Massively Parallel Computation with Low Space

The Massively Parallel Computation (MPC) model is an emerging model which distills core aspects of distributed and parallel computation. It has been developed as a tool to solve (typically graph) problems in systems where the input is distributed over many machines with limited space. Recent work has focused on the regime in which machines have sublinear (in $n$, the number of nodes in the input graph) memory, with randomized algorithms presented for fundamental graph problems of Maximal Matching and Maximal Independent Set. However, there have been no prior corresponding \emph{deterministic} algorithms. A major challenge underlying the sublinear space setting is that the local space of each machine might be too small to store all the edges incident to a single node. This poses a considerable obstacle compared to the classical models in which each node is assumed to know and have easy access to its incident edges. To overcome this barrier we introduce a new \emph{graph sparsification technique} that \emph{deterministically} computes a low-degree subgraph with additional desired properties. Using this framework to derandomize the well-known randomized algorithm of Luby [SICOMP'86], we obtain $O(\log Δ+\log\log n)$-round \emph{deterministic} MPC algorithms for solving the fundamental problems of \emph{Maximal Matching} and \emph{Maximal Independent Set} with $O(n^ε)$ space on each machine for any constant $ε> 0$. Based on the recent work of Ghaffari et al. [FOCS'18], this additive $O(\log\log n)$ factor is \emph{conditionally} essential. These algorithms can also be shown to run in $O(\log Δ)$ rounds in the closely related model of \congc, improving upon the state-of-the-art bound of $O(\log^2 Δ)$ rounds by Censor-Hillel et al. [DISC'17].

cs.DS↗
arXiv2019

SPONGE: A generalized eigenproblem for clustering signed networks

We introduce a principled and theoretically sound spectral method for $k$-way clustering in signed graphs, where the affinity measure between nodes takes either positive or negative values. Our approach is motivated by social balance theory, where the task of clustering aims to decompose the network into disjoint groups, such that individuals within the same group are connected by as many positive edges as possible, while individuals from different groups are connected by as many negative edges as possible. Our algorithm relies on a generalized eigenproblem formulation inspired by recent work on constrained clustering. We provide theoretical guarantees for our approach in the setting of a signed stochastic block model, by leveraging tools from matrix perturbation theory and random matrix theory. An extensive set of numerical experiments on both synthetic and real data shows that our approach compares favorably with state-of-the-art methods for signed clustering, especially for large number of clusters and sparse measurement graphs.

stat.ML↗
arXiv2019

Communicating with Beeps

The \emph{beep model} is a very weak communications model in which devices in a network can communicate only via beeps and silence. As a result of its weak assumptions, it has broad applicability to many different implementations of communications networks. This comes at the cost of a restrictive environment for algorithm design. Despite being only recently introduced, the beep model has received considerable attention, in part due to its relationship with other communication models such as that of ad-hoc radio networks. However, there has been no definitive published result for several fundamental tasks in the model. We aim to rectify this with our paper. We present algorithms and lower bounds for a variety of fundamental global communications tasks in the model.

cs.DC↗
arXiv2019

Leader Election in Multi-Hop Radio Networks

In this paper we present a framework for leader election in multi-hop radio networks which yield randomized leader election algorithms taking $O(\text{broadcasting time})$ in expectation, and another which yields algorithms taking fixed $O(\sqrt{\log n})$-times broadcasting time. Both succeed with high probability. We show how to implement these frameworks in radio networks without collision detection, and in networks with collision detection (in fact in the strictly weaker beep model). In doing so, we obtain the first optimal expected-time leader election algorithms in both settings, and also improve the worst-case running time in directed networks without collision detection by an $O(\sqrt {\log n})$ factor.

cs.DC↗